Deep learning models simultaneously trained on multiple datasets improve base-editing activity prediction

CRISPR-derived base editors (BE) enable precise single nucleotide substitution without introducing double-stranded DNA breaks. Apart from the base editors, efficient base editing strongly depends on both the CRISPR guide RNA (gRNA) efficiency and the editing outcome frequency. Here we show that the accuracy of BE gRNA design can be significantly improved by generating more data and by introducing deep neural networks simultaneously trained on multiple different datasets. Generating ~20,000 gRNAs for A to G and C to T conversions we present such deep learning models, which also allow users to do dataset aware predictions. The methods are available online and as stand-alone software.